Contemporary health systems are increasingly strained by growing complexity, demand, and unsustainable costs. The challenges that threaten the health of populations and the sustainability of our health care systems are increasingly complex. The increasing availability of data on broad factors influencing health and emergence of artificial intelligence (AI), offers an unprecedented opportunity to improve population health and address key health system challenges.
Risk prediction algorithms are a key example of AI applications for population health. The development of risk prediction models using machine learning techniques can bolster existing methodologies, and also unlock previously untenable research approaches to population health challenges. Our team is focused on multidisciplinary collaboration to bring together experts in AI methodologies who traditionally have not worked in the population health space to focus on: (i) developing and testing AI approaches for population risk prediction; and (ii) deploying AI decision-support tools for population health decision-making.
The underlying challenges to deploying AI technologies in health systems are a lack of social acceptability and proven co-design strategies to support implementation in health settings. The CIFAR Solution Network in AI for Diabetes Prediction and Prevention, Co-Directed by Dr. Laura Rosella, aims to address these issues by working collaboratively with policy-, provider-, and community-level stakeholders to develop and apply a framework for Responsible AI in health systems. With our stakeholders, we will co-design and implement socially responsible strategies to deploy diabetes risk prediction tools developed by our team, and enable community health decision-makers to responsibly use the machine learning models to inform trustworthy, relevant and inclusive ways that will improve diabetes prevention, management and health equity.
Dr. Laura Rosella also leads a range of training and capacity building in AI and data science. She is a Co-Director of the pan-Canadian CIHR Health Research Training Platform (HRTP) in Artificial Intelligence for Population Health (AI4PH) hosted at the DLSPH. This national interdisciplinary team brings together trainees, knowledge users, data partners, and community members to co-develop novel training initiatives for AI applications for public health, and to support a critical understanding of AI impact on health inequities. Learn more about the AI4PH Training Program here.
To learn more about our work in Artificial Intelligence and Population Health, please see the following resources:
- Fisher, S., & Rosella, L. C. (2022). Priorities for successful use of artificial intelligence by public health organizations: A literature review. BMC Public Health, 22(1), 2146. https://doi.org/10.1186/s12889-022-14422-z
- Gupta, S. (2019). Classification for Healthcare Using Linked and Unlinked Data Sources [Thesis]. https://tspace.library.utoronto.ca/handle/1807/98054
- Morgenstern, J. D., Buajitti, E., O’Neill, M., Piggott, T., Goel, V., Fridman, D., Kornas, K., & Rosella, L. C. (2020). Predicting population health with machine learning: A scoping review. BMJ Open, 10(10), e037860. https://doi.org/10.1136/bmjopen-2020-037860
- Morgenstern, J. D., Rosella, L. C., Daley, M. J., Goel, V., Schünemann, H. J., & Piggott, T. (2021). “AI’s gonna have an impact on everything in society, so it has to have an impact on public health”: A fundamental qualitative descriptive study of the implications of artificial intelligence for public health. BMC Public Health, 21(1), 40. https://doi.org/10.1186/s12889-020-10030-x
- Morgenstern, J., Emmalin, B., Bornbaum, C., Fridman, D., Kornas, K., Piggott, T., Goel, V., & Rosella, L. (2018). A Scoping Review of Machine Learning Applications in Population Health—Research Protocol OSF Submission.pdf. https://osf.io/https://osf.io/mzq3a
- Ravaut, M., Harish, V., Sadeghi, H., Leung, K. K., Volkovs, M., Kornas, K., Watson, T., Poutanen, T., & Rosella, L. C. (2021). Development and Validation of a Machine Learning Model Using Administrative Health Data to Predict Onset of Type 2 Diabetes. JAMA Network Open, 4(5), e2111315. https://doi.org/10.1001/jamanetworkopen.2021.11315
- Ravaut, M., Sadeghi, H., Leung, K. K., Volkovs, M., Kornas, K., Harish, V., Watson, T., Lewis, G. F., Weisman, A., Poutanen, T., & Rosella, L. (2021). Predicting adverse outcomes due to diabetes complications with machine learning using administrative health data. Npj Digital Medicine, 4(1), Article 1. https://doi.org/10.1038/s41746-021-00394-8
- Rosella, L. C. (2022). Commentary: Deep learning approaches applied to routinely collected health data: future directions. International Journal of Epidemiology, 51(3), 931–933. https://doi.org/10.1093/ije/dyac064
- Yi, S. E., Harish, V., Gutierrez, J., Ravaut, M., Kornas, K., Watson, T., Poutanen, T., Ghassemi, M., Volkovs, M., & Rosella, L. C. (2022). Predicting hospitalisations related to ambulatory care sensitive conditions with machine learning for population health planning: Derivation and validation cohort study. BMJ Open, 12(4), e051403. https://doi.org/10.1136/bmjopen-2021-051403